This work uses game theory as a mathematical framework to address interaction modeling in multi-agent motion forecasting and control. Despite its interpretability, applying game theory to real-world robotics, like automated driving, faces challenges such as unknown game parameters. To tackle these, we establish a connection between differential games, optimal control, and energy-based models, demonstrating how existing approaches can be unified under our proposed Energy-based Potential Game formulation. Building upon this, we introduce a new end-to-end learning application that combines neural networks for game-parameter inference with a differentiable game-theoretic optimization layer, acting as an inductive bias. The analysis provides empirical evidence that the game-theoretic layer adds interpretability and improves the predictive performance of various neural network backbones using two simulations and two real-world driving datasets.

翻译：本工作利用博弈论作为数学框架，解决多智能体运动预测与控制中的交互建模问题。尽管博弈论具有可解释性，但在自动驾驶等实际机器人应用中仍面临未知博弈参数等挑战。为此，我们建立了微分博弈、最优控制与基于能量的模型之间的联系，论证了现有方法如何统一于我们所提出的基于能量的势博弈框架。在此基础上，我们引入了一种新的端到端学习方法，该方法结合了用于博弈参数推理的神经网络与可微博弈论优化层，后者作为归纳偏置发挥作用。分析表明，通过两个仿真实验和两个真实驾驶数据集验证，博弈论层不仅增强了可解释性，还提升了多种神经网络主干模型的预测性能。